Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Computers Shown To Be Better Than Docs At Diagnosing, Prescribing Treatment

Soulskill posted about a year and a half ago | from the boop-beep-you-have-cancer-boop-beep dept.

AI 198

Lucas123 writes "Applying the same technology used for voice recognition and credit card fraud detection to medical treatments could cut healthcare costs and improve patient outcomes by almost 50%, according to new research. Scientists at Indiana University found that using patient data with machine-learning algorithms can drastically improve both the cost and quality of healthcare through simulation modeling.The artificial intelligence models used for diagnosing and treating patients obtained a 30% to 35% increase in positive patient outcomes, the research found. This is not the first time AI has been used to diagnose and suggest treatments. Last year, IBM announced that its Watson supercomputer would be used in evaluating evidence-based cancer treatment options for physicians, driving the decision-making process down to a matter of seconds."

cancel ×

198 comments

Sorry! There are no comments related to the filter you selected.

Just don't ask about airports (1)

MrEricSir (398214) | about a year and a half ago | (#42889309)

You might think it's funny, but Watson is still sensitive about screwing up on Jeopardy a couple years ago.

Re:Just don't ask about airports (1)

Cryacin (657549) | about a year and a half ago | (#42889539)

And will the system consider the patients age/cost to treat/insurance level/likelihood of patient paying future insurance premiums to make up for expenses?

It's just another tool (5, Interesting)

TheCrazyMonkey (1003596) | about a year and a half ago | (#42890035)

And will the system consider the patients age/cost to treat/insurance level/likelihood of patient paying future insurance premiums to make up for expenses?

It will if you program it to. Things like this are tools. As a relatively young doctor (resident) I welcome things like this. Every doctor I know uses reference material, some are printed on dead trees and some are electronic. Today, there's not much difference. But the point it is that there's too much medical knowledge for one person to keep it all in their head at one time. If something like this were to come to market it wouldn't be replacing doctors, it would be augmenting them. Machines do what we tell them to, always have and (hopefully) always will. False rivalries like this completely miss the point. I would love to have a computer algorithm that could correctly diagnose 99% of the time even if it were flagrently wrong the other 1%. That's why humans are in the loop.

Re:It's just another tool (0)

Anonymous Coward | about a year and a half ago | (#42890727)

But how can you tell which is that 1% of mistake. If the computer is correct more often than you are, then by random chance you are more likely to overrule a right answer than a wrong one. Even with an educated guess, you are more likely to overrule a right one than a wrong one; adding "flagarently wrong" isn't that much better because you can still overturn the right decision. I've even been in the situation where I've had something and even though the computers keep spitting that out as an answer, the doctors refused to believe the diagnosis until I pestered them enough to do the simple (but expensive) blood test to check for it.

Re:It's just another tool (1)

Anastomosis (1102421) | about a year and a half ago | (#42890865)

His point, I believe, is "flagrantly wrong" diagnoses are flagrant/obvious enough (such as diagnosing growth plate fracture in an 80 year old or prescribing amputation for pneumonia for instance) that the doctor can then override/run the program again/change parameters/etc. As another resident, I concur with the sentiment. You're right, if the algorithm was subtly wrong 1% of the time, there would be a high chance of overturning a correct diagnosis. What did you have, if I may ask, that a computer diagnosed you and your medical team rejected that diagnosis?

Re:It's just another tool (5, Interesting)

quantumghost (1052586) | about a year and a half ago | (#42891267)

As an attending physician, I have several issues with this article.

A) the slashdot title is a little sensationalistic....never did TFA mention diagnosis without a physician in the loop.

B) by what standards was the final diagnosis discovered (i.e. the gold standard)? Another physician? Another program? Was the trial blinded?

C) this article mentions only one disease process - depression, I fail to accept, blindly, that their results can be extrapolated - that is the crux of medical versus scientific research....see D. Not all diagnoses are obtained by just talking with a patient, in fact short of a psychiatric diagnosis, most require a physical exam....and a competent one. Suppose someone is obviously malingering and complaining about abdominal pain....this system would not pick up on malingering and would likely recommend an operation....a totally wrong diagnosis.

D) this is a retrospective study...in medicine, this is not adequate proof of effectiveness.....you need to perform a prospective trial, preferably with randomization and blinding to adequately prove your hypothesis for treatment. Actually, upon re-reading TFA...it was _simulations_ that were performed. This is hardly world class evidence.

E) cost savings were mentioned, but not long term outcomes....who cares if I saved 75% in the cost of treatment if the patient didn't get better in the end. (yes, short term were noted, but anyone who's ever been on long term therapy knows that the short term does not dictate the long term outcome.

F) In life threatening situations - those that require the most expedient decisions, often with less than complete information, this system would be useless because the patient would die in the time it takes you to input the facts.

G) not all situations are cut and dry. I am often consulted to make decisions about patients that are not addressed in any book. In fact, there may be only 1 or 2 journal articles about the problem, and often there are none. Making a decision treatment in the absence of an established precedent is not going to be one of this systems strengths...."Oh, I'm sorry, I can't help you....I just got the blue-screen of death from the program that was supposed to diagnose you!"

H) would this program tolerate patient autonomy? What happens when the patient refuses some or all of the initial treatment plan?

So, while I point out flaws, it is not to say that this is totally without merit....I am merely pointing out the obvious short coming of this article. In certain fields this could be very advantageous.

I will tell you that in my field, this computer program borders on useless. There is very little doubt about what my diagnosis is, and when I am in doubt, my best evidence is collected by doing something. And computers are really a long way away from matching my skill set. A lot of my diagnosis is made by touching the patient during the physical exam. That exam can completely revamp my decision that started based on the history. And, since I am the one performing procedures, I also would not have a machine dictate the exact method that I use - I am the one performing the operation, I do it the way that I know will result in a safe and effective outcome. In my case, I just don't really don't know what this system would provide to me for patients.

Way to thread jack the first post (0)

Anonymous Coward | about a year and a half ago | (#42890651)

WTF does your comment have to do with airports?

Re:Way to thread jack the first post (2)

draconx (1643235) | about a year and a half ago | (#42891069)

WTF does your comment have to do with airports?

Watson screwed up the Final Jepoardy problem in the first match, which was (category: US Cities): "Its largest airport was named for a World War II hero; its second largest, for a World War II battle."

but who will we sue (0)

Anonymous Coward | about a year and a half ago | (#42889335)

I need money when an honest mistake is made

Re:but who will we sue (1)

Cryacin (657549) | about a year and a half ago | (#42889495)

Why, whomever built the doctor AI, of course!

Re:but who will we sue (0)

Anonymous Coward | about a year and a half ago | (#42890047)

The kid in china that built it.

Re:but who will we sue (1)

gnoshi (314933) | about a year and a half ago | (#42890059)

If the outcome of treatment is consistently better for the automated system than for a human doctor, then the insurance premiums for the automated system will be lower than for a human doctor. Not only that, insurers will not have to worry about whole classes of problems: e.g. inappropriate interactions with clients.

If you add a human cross-checking the output of the automated system to avoid gross errors, then that would potentially help to identify bugs. Frankly, even if there are bugs which cause problems, if the result is still better treatment then that is still a win (for patients).

Modern luddites (5, Insightful)

MPAB (1074440) | about a year and a half ago | (#42889381)

An expected outcome. First machines become good and cheap at performing manual labor, then it's lowly qualified jobs such as sorting stuff or basic accounting.
In a few years, liberal professions will fall. Our salaries (I'm a doctor) have been diving as more and more people around the world can afford a career and achieve a good enough level to perform as a doctor or an engineer.
Creative and risk-taking careers will resist for a longer time.
We can hope for a future of working machines and humans enjoying themselves. The other option will be cheap-ass humans with no way of earning a living whatsoever.

Re:Modern luddites (3, Insightful)

Anonymous Coward | about a year and a half ago | (#42889515)

except software and hardware designers. which is why i'm both. ;)

but seriously, do you really think that's what the future will look like? all evidence from the past shows that as technology gets better, the amount of good jobs goes *up* not down. i don't see any reason why this would change. we're a LONG ways away from having machines do absolutely everything for us.

Re:Modern luddites (1)

NFN_NLN (633283) | about a year and a half ago | (#42889743)

we're a LONG ways away from having machines do absolutely everything for us.

Yeah, what happened to those Japanese sex-bots I keep hearing about?

Re:Modern luddites (2)

superdave80 (1226592) | about a year and a half ago | (#42890139)

The Japanese are keeping them all for themselves. Wouldn't you?

Re:Modern luddites (5, Insightful)

Garridan (597129) | about a year and a half ago | (#42889749)

Meh. You can be replaced by sufficiently advanced algorithms. I'm mathematician, FFS. There are already automated theorem provers which can solve undergrad-level problems. As computers evolve, they'll be just as good as people and loads cheaper than people at everything we do, up to and including the creation of art.

If we progress to the point where all of our jobs can be done by computers... what should we do? At the point where artificial intelligence becomes genuine intelligence, it will rapidly outpace human intelligence. This is evolution. We are breeding our replacements.

Re:Modern luddites (-1)

Anonymous Coward | about a year and a half ago | (#42889815)

if i could be replaced by a sufficiently advanced algorithm i would have been already.

oh, you meant in the far future, long after i've been dead? sure, you're probably right. but i won't care by then. :P

i really do think we're quite a long ways off from artificial intelligence on the level you're talking about.

Re:Modern luddites (1)

Garridan (597129) | about a year and a half ago | (#42890261)

You don't seem to understand the word "sufficient". And that future may not be as far off as you think. Then again, it may be.

Re:Modern luddites (1)

Garridan (597129) | about a year and a half ago | (#42890355)

All it takes is one genius to figure it out. With flat, serial processors (even billions of them), we're probably hundreds of years away. With processors built from components that work like (even simple) neurons... who knows.

Re:Modern luddites (1)

PingPongBoy (303994) | about a year and a half ago | (#42891469)

>> If we progress to the point where all of our jobs can be done by computers... what should we do?

In the future cheap unprofitable or low-margin jobs that machines will do (that might include a lot of things that today's highly-paid people struggle with) will have to be run by government. No one else want to do that work anyways.

People will want to be in control of things that matter, things that are challenging, such as finding a way to move out of the solar system. Even the computers will agree to that.

Re:Modern luddites (2)

canadiannomad (1745008) | about a year and a half ago | (#42889813)

Yeah, I kinda predict that the jobs of doctors will move to collecting the information the computer asks for, volunteering info that they notice from experience/sight/interaction (try a computer on a mental disease patient...) And whenever the diagnosis is wrong the doctor would do research and/or try to teach the computer what other questions steps would be required to detect and treat the special case.. That way it is improving the system for everyone. Also the computer could be smart about how it prescribes anti-biotics and the like as to reduce the possibility of drug resistant strains.

Re:Modern luddites (1)

shaitand (626655) | about a year and a half ago | (#42891349)

I can't see this obsoleting doctors.

An implementation could be built that works in a manner similar to Bitcoin but instead of cracking hashes you are performing encryption and doing processing of statistical analysis and cross indexing of data in a completely decentralized manner you could build an anonymous, safe, secure, and global system that potentially could gather statistically significant data on a scale that makes FDA controls and studies look like random speculation.

It could build a biometric fingerprint to assure no duplicate users. It would have a mining component for processing and check-ups but charge for diagnosis, After the diagnosis is complete it produces two printable QR codes one that retrieves the diagnosis and statistical evaluation and another that redeems for the cost of the diagnosis. So the system says you need a script, you go to a doctor, the doctor writes a script or orders the requested test or whatever and you give him the QR code. Otherwise you just credit the QR back to yourself. Doctors can double as exchanges. Implement a feedback mechanism to rate doctors and a fee to be listed as a doctor, the system dynamically adjusts the fee with the assumption that higher fees reduce the number of doctors who do not redeem significant quantities of QR codes. The currency system is essentially backed by Healthcare.

Here in the states any geek could produce a molecule, bundle it with an herb and sell it as a supplement. You are immune from liability as long as you made no claims but if people use your drug and report it to this system it will eventually start recommending it for you for anything it has shown statistically significant effectiveness for. It figures out drug interactions, it continues statistical analysis. Every person ever using it becomes a long term study subject. Since the geek can already do this legally but can't legally demonstrate effectiveness this is all upside.

This has the potential to turn the drug industry on its head. It doesn't prevent governments from regulating medications and treatment options and making sure patients can use government funded treatment options but gives you a way to build the benefits of decentralized facts based self regulating capitalism on top of it.

Re:Modern luddites (1)

Desler (1608317) | about a year and a half ago | (#42889545)

We can hope for a future of working machines and humans enjoying themselves.

Hahaha, good joke.

Re:Modern luddites (0)

Anonymous Coward | about a year and a half ago | (#42889843)

Yep, just like they said in the 50's look for the -rich- to have working machines. Everyone else ? Fuck them, let them eat cake.

Re:Modern luddites (1)

shaitand (626655) | about a year and a half ago | (#42891361)

No kidding. We live in a world where any drug with reported effects of Euphoria lists them as a severe negative side effect and it likely to be more tightly controlled.

Re:Modern luddites (1)

Anonymous Coward | about a year and a half ago | (#42889581)

interesting, last time I went to the doctor she barely looked at me and just typed up what I was saying into the computer. Now I realise it was probably google!

Re:Modern luddites (1)

0123456 (636235) | about a year and a half ago | (#42889937)

The last few times we've had to go to a doctor we already knew what the problem was and what to do about it from Google, we just had to get the doctor to sign the prescription form. I've been convinced for years that 90% of what doctors do could easily be replaced by software.

Re:Modern luddites (2)

ColdWetDog (752185) | about a year and a half ago | (#42890575)

Probably. It's the other 10% that's the bitch.

Re:Modern luddites (1)

frank_adrian314159 (469671) | about a year and a half ago | (#42889887)

We can hope for a future of working machines and humans enjoying themselves. The other option will be cheap-ass humans with no way of earning a living whatsoever.

Call me a pessimist, but I'd bet on the second happening before the first.

Re:Modern luddites (1)

shaitand (626655) | about a year and a half ago | (#42891019)

No worries. This has the potential to reduce the impact of having controlled substances which means it will never happen in a way that doctors need to worry about.

The problem is the most evil of all negative side effects. Euphoria! A computer AI running as a cellphone app wouldn't prescribe things without a cause but it also wouldn't police patients. That would be the excuse at least and never mind that the AI as a gateway to scripts guarantees screening for drug interactions and informed choices thus eliminating any excuses that could trump their right to make their own choice about what to put in their body.

Most likely the software prescribing anything will be seen as self-prescription because people are in denial about just being an AI themselves. So AI scripts probably won't be allowed in the first place. They will require you to take the recommendation to a doctor. So the general practitioner will continue to fill the same primary capacity, he will be a drug dispenser and liability holder. They will probably FDA regulate the software itself saying it is a physicians diagnostic tool and require a certified hardware platform for it. It will be expensive as hell but doctors will love it because the FDA certification will make them proof against lawsuits as long as they use it.

The Pharma industry also likely knows no algorithm given a free choice would end up prescribing their latest molecular tweaks. Statistically the generic older drug will work comparably and it mathematically doesn't make sense to prescribe something with less tracked history unless it has shown significant benefits over the old drug with the expired patent. If you let the AI analyze and discover treatments instead plugging in controlled FDA studies as statistical data instead of locking it to FDA recommendations it could analyze the health information of everyone who reports using any substance with the ability to get the result of controls through cross indexing data from routine checkups and sheer stupidly massive sample size. In most cases it would have as much or more data on unregulated herbal remedies/supplements, vitamin supplements, over the counter medications, diets, etc and would be able to find if and where they are effective and what their interactions are without any need to care about isolated molecules. If a chem geek isolated a molecule from a traditional herbal remedy and sold it as a supplement and it turned out to be more effective than the top cholesterol medication it could well end up being recommended nationwide without any FDA red tape and because the software and not the seller is advocating the effectiveness the seller would enjoy the same sort of immunity to liability a drug company enjoys. If he changed manufacturing in a way that reduced effectiveness that would automatically show up in the stats. And it would be global data not merely US data. Yeah big Pharma would never allow any of this to happen and neither would the FDA.

It's a nice dream. Maybe someone will build a network version that is open source and completely decentralized and can't be regulated after being kick started. It wouldn't be able to prescribe but nothing would stop it from collecting data about scripts and comparing it to reported data. If it grew large enough and it's effectiveness well known the result could be mostly the same. Then doctors could prescribe off label using the data and could point to the known reliability of the system to mitigate reliability.

Re:Modern luddites (1)

shaitand (626655) | about a year and a half ago | (#42891029)

Sorry, s/reliability/liability/ at the end there. Probably lots of other typos in that rant too.

hmmm, who should we trust? (1)

Anonymous Coward | about a year and a half ago | (#42889401)

Big Pharma driven medical reps, motivated by insurance/lawsuit dodging and prescription kick-backs, or a heartless robot driven by a growing database of real-world evidence?

Best path remains: don't get sick.

Re:hmmm, who should we trust? (1)

couchslug (175151) | about a year and a half ago | (#42891125)

I don't need a fucking "heart" or bedside manner, I need precise, correct medical information processing so decisions can be made swiftly and correctly.

"Best path remains: don't get sick."

Tough shit. Barring murder or suicide etc, we will all "get sick".

Not what doctors want to hear (2, Insightful)

Anonymous Coward | about a year and a half ago | (#42889407)

I'm sure this is not what diagnosticians would like to consider, but I think the simple truth is that computers will negate our need for human diagnosis in the very near future. I'm sure we'll hear the same "The computers will be great *assistance* to actual doctors" but I don't think that's actually true. I know the computer is likely doing a better job, there should possibly be a few overseers but the vast majority of doctors shouldn't be needed, and frankly I wouldn't want them second guessing what's likely to be a much more accurate and unbiased diagnosis given by the machine.

GIGO (3, Insightful)

erice (13380) | about a year and a half ago | (#42889623)

An expert system is only as good as the information it is fed. Until we get machines that can quickly scan a human body and tell us everything there is to know about it, we will still need doctors to talk to patients, vet what they say, observe what didn't mention and ask followup questions.

Re:GIGO (1)

Dunbal (464142) | about a year and a half ago | (#42889753)

And tell you what the patient is NOT telling you. Medicine is based more on objective observations than subjective answers to questions. While 85% of the diagnosis is usually in the medical history, do we just let the other 15% die?

Re:GIGO (1)

Anonymous Coward | about a year and a half ago | (#42890101)

and an expert system can't do that? say running a terrahertz scanner, an IR probe, MRI imager, X-ray imager, blood anaylsis system, etc. Most of this stuff is done with electronic tools anyway, and most of the cost of the test is the human performing it and paying off the loan for the equipment.

  An autoDoc system based on a watson with these tools could do everything short of surgery, and that require advancements in machine vision and machine control systems before that could be done.

2050, and the only humans in the medical industry will be in research, specialists, and Counselors.

Re:GIGO (0)

Anonymous Coward | about a year and a half ago | (#42890063)

Ah, but a doctor is only as good as the information he gets and a machine can take in far more information. It's all about pattern recognition whether you're using a biological brain or a silicon chip. Of course people might be more comfortable if the machine wore a white coat [psychologytoday.com] .

Re:Not what doctors want to hear (2)

buybuydandavis (644487) | about a year and a half ago | (#42889673)

Ha! This is just another technology that the medical industry will control to suck money out of us. Here's what's going to happen.

Machines will "assist", but as "medical devices", only medical vested interests will have legal access to them. Our health care will improve, while we *continue* to get robbed by the medical industry through the rent seeking made possible by licensing laws.

Re:Not what doctors want to hear (1)

PRMan (959735) | about a year and a half ago | (#42889875)

So, you don't want your medical diagnosis machine tested by the FDA to ensure that it's as safe as can be? You don't want to be able to sue a large, wealthy organization for malpractice leading to your death?

Re:Not what doctors want to hear (1)

Anonymous Coward | about a year and a half ago | (#42890039)

You have to have to money to go to the Doctor. Would you want No Health Care, or Free but can't sue?

Re:Not what doctors want to hear (2)

buybuydandavis (644487) | about a year and a half ago | (#42890233)

Ha ha. No, I *don't*.

Sorry, I've worked in the medical device industry. FDA tested does not mean safe and effective. Companies work around regulations, making their products less safe, but able to pass testing. At best the regulatory process only delays medical progress a decade or so and multiplies costs ten times, and at worst it completely prevents improvements for decades.

How is it that grown ups can think government apparatchiks colluding with corporate rent seekers is a recipe for effective health care?

I want what google or IBM can provide today. That's what I *want*.

But what you or I *want* is hardly relevant. It's what those in power want that matters. FDA apparatchiks like their jobs, they like their power, and they like the money they make when they move to jobs in the industries they regulate. Similarly, the industries like protected and regulated markets and the opportunities for rent seeking it brings.

Everyone's a winner! Well, everyone that counts - those in power. Patients get robbed and die, but they don't have power, and many of them are fools besides, licking the hands that beat them.

Re:Not what doctors want to hear (0)

Anonymous Coward | about a year and a half ago | (#42890807)

How is it that grown ups can think government apparatchiks

That's funny.

Re:Not what doctors want to hear (1)

jbmartin6 (1232050) | about a year and a half ago | (#42891081)

What does what the parent mentioned have to do with the ability to sue for malpractice?

Interesting (4, Interesting)

Intrepid imaginaut (1970940) | about a year and a half ago | (#42889425)

I find this interesting, I was wondering when we'd reach the point where the accumulation of knowledge available in any given field exceeded the ability of the human mind to completely grasp in a useful manner. It's going to reach a situation where multiple experts on a given subject with a fair idea about related subjects are going to be the only unit capable of actually doing anything sooner rather than later - apparently in medicine at least computers have come to the rescue.

I suppose with the many specialisations in every area we're already there, the question is can we repeat the improved returns in areas like physics and chemistry.

Re:Interesting (4, Insightful)

joh (27088) | about a year and a half ago | (#42889483)

The problem is not in the decision making process, but in the fact finding process. THIS is the part computers and software are still very, very poor at.

Re:Interesting (2, Informative)

Anonymous Coward | about a year and a half ago | (#42889611)

Sadly, so are most general doctors.

Re:Interesting (1)

Dunbal (464142) | about a year and a half ago | (#42889775)

Seconded. Most, but not all.

Re:Interesting (4, Interesting)

ColdWetDog (752185) | about a year and a half ago | (#42889833)

We could start by getting some real information instead of the pair of nearly identical fluff pieces in the TFA. While it's nice they used Markov Decision Chains, as best as I can tell they did a bunch of simulations with pre existing data and came out with 'better' information than the docs who, unfortunately, were dealing with problems in real time.

The lawyers have had this sort of thing for years. It's called a 'retrospectascope'. It tells you what you SHOULD have done after you know what the outcome is.

Very, very helpful. To lawyers anyway, to doctors, not so much.

I'd love to see some real computerized decision analysis that would be useful in real time medicine. I'd love to have "all" of the information about a patient in real time.

I'd also like a Pony and one million dollars. Before I get worried about job security and before everyone goes all Star Trek, lets see if this works in a real clinical setting.

Re:Interesting (1)

PRMan (959735) | about a year and a half ago | (#42889903)

Looking online is already more accurate than many of the poor-quality doctors that I see these days. Good doctors are, of course, much better than reading yourself online. This technology in combination with a doctor would be very powerful. It would even be better as a means of rating doctors that disagree with the machine and are right or wrong in those instances.

Re:Interesting (1)

schlachter (862210) | about a year and a half ago | (#42890149)

I think a major problem with the current approach is communication. Doctors rarely communicate with each other and for cases where a patient is trying to figure out what's wrong with them and getting bounced around by specialists, no one really has the full picture, not even the primary.

A computer can have the full picture, assuming there is enough data for it to churn on, and given enough population data to train on, it inevitably will arrive at evidence based diagnosis and treatment options better than any human...for the stuff that's understood.

Re:Interesting (1)

ColdWetDog (752185) | about a year and a half ago | (#42890643)

A computer can have the full picture, assuming there is enough data for it to churn on, and given enough population data to train on, it inevitably will arrive at evidence based diagnosis and treatment options better than any human...for the stuff that's understood.

Where exactly in this magical, cornocopian world, does the computer get the 'full picture'? There is this odd feeling around here that if you feed enough information into 'the computer' it will solve all sorts of difficult problems automagically. Not going to happen. Yes, it's true that data collection needs to be standardized and analyzed. That can give you suggestions where to look. But correlation is not causation and correlation is what these programs do.

That and the fact that diagnosis isn't always the hard part. Ask any neurologist. They can diagnose all sorts of diseases with scary names and scary outcomes. When you ask what you can do about them, they shrug their shoulders. Dr. Omnipotence isn't going to have an answer.

Re:Interesting (1)

mspohr (589790) | about a year and a half ago | (#42890923)

Medicine has always had this problem. It is a large complex field with constantly evolving "truths".
Computers are much better than humans at considering all of the options.
An early pioneer in this field, Larry Weed, used to say that a good clinician could come up with a 3 item list for a differential dx and an expert could come up with 6 items. However, the computer can come up with 20 along with a list of tests to perform to make the final dx.
Computers have consistently been shown to perform better than humans for medical dx but the hubris of the medical profession prevents their adoption.

Re:Interesting (0)

Anonymous Coward | about a year and a half ago | (#42891461)

I think this happens pretty regularly. The response is to create a smaller niche. So as the sum of knowledge gets bigger, so the depth of knowledge in a person gets deeper and narrower.

And yes, this then requires teams to get together and collaborate to solve interesting problems. Look around; big problems are solved by teams, not by individual geniuses. And the next step is we start to get people whose knowledge base is getting niche "knowers" to share and collaborate.

Is there a role fore the generalist in all this? That's what I've always wanted to be...

Just another pdr (1)

alen (225700) | about a year and a half ago | (#42889459)

I have 2 kids and my first one was always sick until a year ago. He was on antibiotic at least once a month

After a while I picked up on a few things

There is a simple 5 point check to see if the llllness is bacterial or viral
Once he diagnoses the doctor does not choose the drug. The physicians desk reference aka pdr tells the doctor what to prescribe
The dosage is determined by the drug companies depending on the child's weight

The pdr will have every known disease, illness, condition and the drugs or procedure required to treat it

Re:Just another pdr (1)

Anastomosis (1102421) | about a year and a half ago | (#42890951)

Yeah, the real genius of the infectious disease docs is not the routine viral/bacterial check, nor the pharmacology. It's the advanced and rare stuff that have subtle manifestations, and dealing with all the co-morbidities.

Mycin (4, Informative)

White Flame (1074973) | about a year and a half ago | (#42889523)

In the early 1970s, Mycin [wikipedia.org] achieved 69% accuracy of prescribing a "correct" treatment for a patient's condition, which was deemed better than human specialists.

The linked articles don't seem to include the absolute accuracy that it achieves, just the relative accuracy against doctors. I wonder if we've come any further than the basic expert system rules allowed 40 years ago.

Re:Mycin (1)

Anonymous Coward | about a year and a half ago | (#42889735)

Mycin's basic expert system rules might be good enough. The hardware advance are more important. We have 1 Ghz processors & huge RAM today compared to 2-5 Mhz in the late 1970's. Also, we have cheap sensor to actually input the dat directly from the patient into the system, reducing human typing errors, etc.

Re:Mycin (4, Informative)

cbhacking (979169) | about a year and a half ago | (#42890107)

Came here to mention this. Medical "expert systems" (a class of AI) have existed, and been better than humans at some things, for literally decades. However, you almost never hear about them anymore. With the vast advances in processing power, miniaturization, and power usage, we can today build pocketable devices that tremendously exceed the capabilities of something like Mycin. With the improvements in sensor technology, we can feed those systems more and better data than ever before. With widely available wireless Internet connectivity plus incredible storage densities, we can provide these systems with all the info they could ever need. With the advances in the science of AIs over the last four decades, we can make these systems "smarter" than was possible before. Finally, with the plummeting cost of such electronics, we can make such systems affordable to middle-class individuals, rather than exclusively to large and well-funded organizations.

Yet, they almost non-existent. We have a few smartphone apps that scratch the surface of what's possible. We have dedicated machines like continuous glucose monitors for diabetics, but they have very little in the way of smarts and no versatility. We have concepts and pseudo-prototypes of "medical tricorders" and such sci-fi devices, but they aren't generally set up to make recommendations. We have online web applications where users can input symptoms and be told what they might be, but those systems have no personal background or history of the user's health, and rely on the user measuring and providing data themselves.

Why haven't these things been combined?

Re:Mycin (4, Insightful)

0123456 (636235) | about a year and a half ago | (#42890143)

Why haven't these things been combined?

Who could possibly be opposed to cheap, automated healthcare?

Re:Mycin (1, Interesting)

Tailhook (98486) | about a year and a half ago | (#42890513)

Who could possibly be opposed to cheap, automated healthcare?

Doctors [ama-assn.org] . Obviously.

People that can do math see Obamacare as infeasible [latimes.com] given current practice and the number of practicing doctors. Doctors vociferously oppose [fiercehealthcare.com] delegating anything, however.

We're going to have to break the doctor monopoly in the US. The cost has gotten too high to indulge this exclusivity any longer. Automation, nurse practitioners, whatever. It's got to end. If there is anything good about Obamacare it is that this issue will be forced.

I don't wish to see Doctors punished, but the fact is that tens of millions of people are about to arrive in their offices with uncancel-able, no-lifetime-limit, fixed-rate Obamacare and a lifetime of accumulated, untreated damage. At the very least this is going to force a LOT of delegation.

Physics. It's a bitch.

Re:Mycin (1)

ColdWetDog (752185) | about a year and a half ago | (#42890675)

OK, answer this: The REST of the world, including some really smart folks in some very advanced countries have yet to make the magical tricorder. You'd think SOMEBODY could do it - it doesn't have to be an American invention.

The fact that magical tricorders and snazzy, useful expert decision systems aren't available just might mean that the human race, in aggregate, hasn't got to the point where such devices are feasible.

Re:Mycin (4, Interesting)

Tailhook (98486) | about a year and a half ago | (#42890893)

No need to go overseas. The Veterans Administration under the US DOD uses so-called nurse triage lines with an expert system to direct patients to care over the phone. They're making a mobile, tablet [govhealthit.com] based system now:

The combined solution, called ER Mobile, will make it possible for nurses to perform timely, accurate triage on a mobile device anywhere in the ER, as well as create a comprehensive record that will be recorded in the VA EMR.

Shazam. Tri-corder.

The VA isn't nearly as slavishly obedient to the AMA as private practice, and they definitely don't have employer provided health insurance systems to bilk, so things like this (delegation to nurses) get traction.

Re:Mycin (1)

0123456 (636235) | about a year and a half ago | (#42891345)

OK, answer this: The REST of the world, including some really smart folks in some very advanced countries have yet to make the magical tricorder. You'd think SOMEBODY could do it - it doesn't have to be an American invention.

Most of the Western world has socialised medicine, and they have a very strong incentive to not put themselves out of work; if I remember correctly, Britain's National Health Service is the largest single employer in the EU.

And in the rest of the world, a doctor is probably cheaper than a computer.

cheap, automated healthcare? (0)

Anonymous Coward | about a year and a half ago | (#42891547)

Cheap, automation is one reason we need healthcare. Before escalators, elevators & cars, we all got much much more exercise. Before mass produced candy bars & fast food, we ate much much better.

Re:Mycin (4, Interesting)

AaronLS (1804210) | about a year and a half ago | (#42890527)

I'm believe they are in slightly diminished roles. The US military has triage lines, where family members call in about medical problems, a registered nurse answers and then decides if the patient should self-care, book a Dr. appointment, or go to emergency room. I handled appointment booking, and sometimes the nurse would call and no appointments would be available and they'd get annoyed at me and say "Well that's what the computer told me to do."

I figured they had some sort of system that the nurse entered symptoms into, and it used the patient history+symptoms to suggest a self-treatment or triage to appointment/emergency room. I had also read about these systems in the book AI: A Modern Approach Even when the doctor doubted the diagnosis, the computer could even explain the conclusion(this is pretty advanced for an expert system) which would usually elicit a kind of "oh I didn't consider that factor" kind of realization from the Doctor.

I assume a registered nurse must still be involved to meet legal requirements, to properly elicit symptom information, and serve as a sanity check for the system. The problem, demonstrated by their response and inability to troubleshoot problems, is that they become completely trustful of the system. I imagine the opposite problem is also common, where they don't trust the system at all.

big difference in technologies.. (2)

schlachter (862210) | about a year and a half ago | (#42890245)

The big difference here is in technologies.

Mycin used a bunch of rules to arrive at medical decisions. These had to be manually entered by medical experts which is time consuming, difficult, and outdated by the time it is completed. It was a narrowly focused, brittle system that strived to emulate the logic of it's designers.

The newer approaches (like the kind from this article) build their own probabilistic models of medical diagnosis and treatment based on statistical analysis of data. Lots and lots of data. Data that would have taken hundreds of years to process in the 1970s. From this, they learn what works and what doesn't and under what circumstances independent of the knowledge of its designers. In effect, it can be better than its creators.

Re:Mycin (2)

Alomex (148003) | about a year and a half ago | (#42891219)

In fact computers have been far superior at medical diagnosis for about ten years, and there are several products commercially available. The only reason they are not routinely used is because doctors fear for their jobs.

People have died because the doctor did not run the diagnosis against the computer. Let's face it day to day medicine is nothing like "House" were they get together and debate your case. If you are not responding, doctors usually just carry on with more of the same treatment and hope for the best, while the computer would say "patient not responding to Randomicine? then check the zootocite count for possible inflammation of the hyperbolerium" and in that case one of two things happen: we discover it's the hyperbolerium and treat you for that or we determine it isn't that and continue the normal treatment on the basis of actual evidence instead of just a hunch.

Virtual Doctor you got leprosy (1)

Joe_Dragon (2206452) | about a year and a half ago | (#42889699)

Virtual Doctor you got leprosy

Second Opinion (1)

sunderland56 (621843) | about a year and a half ago | (#42889703)

So, who do we consult for a second opinion? HP? Oracle?

Re:Second Opinion (1)

Kittenman (971447) | about a year and a half ago | (#42889879)

So, who do we consult for a second opinion? HP? Oracle?

Well, people used to go to (the) Oracle for a second opinion in the old days (ba-dum-cha)

Re:Second Opinion (1)

PRMan (959735) | about a year and a half ago | (#42889919)

It doesn't matter. They're using the same system so the second opinion is very similar to the first. Eerily similar. Deja vu, in fact.

Old tech (4, Funny)

drcheap (1897540) | about a year and a half ago | (#42889765)

I don't care what this article says, this is nothing new. My in-home psychiatrist in the 1990s was great at diagnosing my issues. Perhaps you were a patient of his, too? His name was Dr. Sbaitso [wikipedia.org] .

Re:Old tech (1)

drcheap (1897540) | about a year and a half ago | (#42889773)

Errr, I meant psychologist. Big difference!

Idiocracy here we come (2)

dethndrek (870145) | about a year and a half ago | (#42889825)

"This one goes in your mouth, this one goes in your butt."

Because doctors are humans. (5, Insightful)

Anonymous Coward | about a year and a half ago | (#42889837)

The problem with doctors is their ego. Being a nurse for quite some time Ive seen countless doctors come through the hospital that do not treat a patient properly, ignore patient complaints, dont treat problems aggresively enough, are too passive, and so on and the vast majority of them refuse to do otherwise because of their ego. They are doctors, no one should question them and they hate it when you do and when you do they dig their heels in and dont budge. Doctors are also human so they get tired of their job, they get lazy, they stop caring after awhile, they worry more about what they will do later than the problem at hand, they stay up too late.

Ive also seen countless times people who swear by these doctors and will accuse of them of fault simply because the doctor has been nice to them. A doctor who is friendly can do no wrong in a patients eyes. Or a patient has some common problem that even a moron could treat, then when the doctor fixes them suddenly they become godlike.

Personally I would trust the diagnosis of a machine that has more information programmed into it than a thousand doctors do collectively from allover the world.

A machine can be a doctor because thats how doctors are trained, they are trained to be machines. They treat the problem, they do not treat the person. Treating the person is a nurses job. And treating the problem is simply nothing more than deduction. If patient has multiple problems then you take those numbers and it will lead you to the correct answer. Thats all being a doctor is, you look at the signs and symptoms, then you add them alltogether and you get the answer as to what the cause is. Its all a forumla and nothing more, there is no great mystery to it.

Re:Because doctors are humans. (2, Insightful)

Anonymous Coward | about a year and a half ago | (#42891017)

Haha, spoken like a true bitter nurse. Believe me, as a physician, there are plenty of my colleagues with huge egos. Definitely. And with many diagnoses, they are indeed bread and butter, no-brainer treatment algorithms. But to generalize and say that applies to all patients, with all conditions, and there is no underlying mystery or art ever, is just well... quite far off the mark. Especially in a tertiary care referral center where all the rare and complicated cases come.

To be expected - and not anti-docs (1)

udippel (562132) | about a year and a half ago | (#42889883)

Serious. Logic kind of dictates this to have happened.
It does not mean that doctors are worse than the system; on the contrary: doctors are those fantastic deliverers of input to this expert system.
Of course, a medical system that has all sorts of medical information, treatments, medicines, and potentially millions of case histories provided by human doctors will evaluate chances, correlations and success probabilities much much faster and much better than the family GP. So what's new in here? Maybe that the computer systems are now available to actually do these calculations.

Same old objection (5, Insightful)

pclminion (145572) | about a year and a half ago | (#42889933)

Apart from doctors who will understandably not want to be rendered obsolete (and they won't be -- the computer can only prescribe a treatment, not administer it!), the main objection that would be raised to this is "What if the computer makes a mistake?" For some reason, people are really bad at understanding that even though the computer might make a mistake, it will make mistakes at a lower rate than a human. This is the same problem with computer-driven automobiles. Yes, the computer might screw something up and kill somebody, but this should happen at a much lower rate than caused by human drivers -- however, because the rate isn't EXACTLY ZERO it is seen as completely unacceptable, even though this is an irrational position to maintain.

Re:Same old objection (1)

Anonymous Coward | about a year and a half ago | (#42890097)

My bigger concern isn't _if_ it makes a mistake, it will. My concern is with who takes the blame? Will the machine be overseen by a doctor who must confirm the machine's finding and recommendations? Will the software developer or hardware engineer carry any fault? Can the maker of a machine doctor be sued for bad treatment? I think the answers to those question will be interesting if this technology is adapted.

Re:Same old objection (2)

jmv (93421) | about a year and a half ago | (#42890603)

And the solution to both objections (including doctors not wanting to be obsolete) is to have the machine *assist* the doctor, in a similar way that auto-pilots assist but do not replace pilots.

Yeah, just like flying is safer than driving (1)

Anonymous Coward | about a year and a half ago | (#42889949)

If you suck as a doctor or driver then these things are true. Unfortunately most people suck at everything.

I really good doctor can beat the odds just like a really good driver can. It's not even about being better than average, it's about actually being good at what you do. Very few people fall in to that group.

Re:Yeah, just like flying is safer than driving (1)

thesupraman (179040) | about a year and a half ago | (#42890091)

Great!

Now, can you just let me know how to avoid the car that suddenly swerves from the opposing traffic in to the front of me?
And while you are at it, what to do when the car sufferes a critical mechanical failure at speed, ramming me straight in to a power pole?
Since you are such a good drive, you must know something I dont..

Of course some are better (a lot better even) than others, just pointing out that doesnt help driving be safer than flying, not even close.

Re:Yeah, just like flying is safer than driving (3, Insightful)

Anonymous Coward | about a year and a half ago | (#42890313)

Cars with human drivers are the only ones that suddenly swerves from the opposing traffic lane in front of you. And at least 1/4 of the time, those human drivers are drunk too! And quickly getting more than 1/4 of them distracted on their cell phones, as if one can read phone texts and type while they drive!

I'd take my chances with a computer controlling a car any day over the current system of allowing human drivers who daily make mistakes and kill 40,000+ Americans PER YEAR on the highways and streets!

Drug Companies doing away with doctors (5, Interesting)

anthony_greer (2623521) | about a year and a half ago | (#42890015)

This sort of thing is just what big pharma wants, no human interaction and careful consideration, just a pill dispenser...symptom a + symptom B == Pill 2...
How much you wanna bet this thing always prescribes expensive non generic drugs and never tries the 50-70 year old known treatments that are usually the first steps in treatment before new expensive drugs are prescribed.

Also, anyone notice the change in medical advertising and communications, they never say "ask your doctor" any more, its ask your prescriber, or ask your provider...like they want to dis-intermediate doctors and are getting the public ready.

Re:Drug Companies doing away with doctors (1)

gringer (252588) | about a year and a half ago | (#42890965)

This sort of thing is just what big pharma wants, no human interaction and careful consideration, just a pill dispenser...symptom a + symptom B == Pill 2...
How much you wanna bet this thing always prescribes expensive non generic drugs and never tries the 50-70 year old known treatments that are usually the first steps in treatment before new expensive drugs are prescribed.

It's more difficult to bribe computers, so I'd doubt this is what big pharma wants. A properly designed diagnosis system (open source, or government-managed) should offer the cheapest efficacious drug, rather than the latest drug that has been shown to be more effective than a placebo (but curiously untested in effectiveness against the most effective generic drug).

The problem with a computer diagnosing... (4, Insightful)

CannonballHead (842625) | about a year and a half ago | (#42890127)

... is that the computer doesn't have, literally, hands-on experience.

For example... you have stomach pain. Okay. Where? Does this hurt? Does it hurt if I poke this? Do you have a fever? How high? ("Oh, I don't know, maybe XX" ...)...

In other words, you still need someone who *knows* what to do to help diagnose simply to *get* the information. You need someone trained to know where to poke, where to tap, where to see if something hurts. And then, of course, to try to wheedle the real information out rather than the confusing answers patients (note that I am not a doctor, I am a patient) give. :)

As a diagnostic tool, I think it would be a huge benefit. An individual simply can't keep up to date on everything, don't know everything, and can't research everything. Having a diagnostic tool that *does* do all that would be a huge benefit. There would be options and diagnoses that perhaps the doctor had not thought about. Additionally, the diagnostic tool - I hope! - would not just say "Oh, it's this" but would perhaps say "Well, it could be this, and you need to find out this information first ... or it could be this, and for that you need to do these tests..."

The idea that a patient, combined with a non-trained non-doctor, can somehow come up with all the right answers/information and a machine can simply diagnose it on the spot seems like a very simplistic view. Perhaps that works with colds, the flu, or warts... but for more complex things... it seems diagnoses tend to work on a "it could be this; let's do more specific tests to find out if it is" type of investigation.

Re:The problem with a computer diagnosing... (1)

Anonymous Coward | about a year and a half ago | (#42890523)

All of these are programmable...

Re:The problem with a computer diagnosing... (1)

Anonymous Coward | about a year and a half ago | (#42890733)

.... or can be performed just as well (if not better) by a nurse that is being payed five times less than what the doctor gets. Now excuse me I need to buy some IBM stock.

Weather (1)

HalWasRight (857007) | about a year and a half ago | (#42890135)

Perhaps Drs could use a tool like this similar to how weather predictions are done. Run the model(s), and use human analysis to weigh the data.

Sad that this is true (2)

SCHecklerX (229973) | about a year and a half ago | (#42890189)

In my experience, most doctors don't really think about problems, but just look at historical remedies and prescribe those particular drugs. They just regurgitate what is in the books. If you have something new or multiple problems (I've been dealing with this for a year now, with no relief in sight), I think I'd rather listen to watson. These guys have cost me thousands of dollars and all of my vacation time and I'm worse than when the problems started.

Re:Sad that this is true (0)

Anonymous Coward | about a year and a half ago | (#42891047)

I'm confused. How is Watson going to come up with a solution to your illness that is not in the books?

Part of the Electronic Records Movement (1)

Anonymous Coward | about a year and a half ago | (#42890221)

Electronic medical records are unfortunately not up to where they should be. It baffles my mind that pertinent information is still kept in a paper based chart bigger than a phone book for the majority of health centres. My hospital is trying to make a big movement, with a large optimization project. All patient armbands are as they were before, except they also come with a barcode. The idea is regular meds are linked to a patient barcode, and when both armband and med packet are scanned medication errors are prevented. Equally this system serves to immediately chart what the patient received and when.

This is important, as histories and results are all fed into the same system. The gold standard of treatment is listed, along with alternative treatment options, in a drag a drop like system. While this has the potential to create "brainless" medicine, it also prevents things from slipping through the cracks. For example, say a patient comes into the ER with abdominal pain. The system will spit out a differential diagnosis, in order of probability and list the required labs, tests, medications and interventions for each diagnosis. As test results come back, the diagnosis list diminishes. Equally it makes sure patients are receiving that dose of antibiotics that evidence based decision making has determined is the best course of action in most circumstances. It also knows that this organization has switched to a new antibiotic as the other previously used four months ago was known to cause minor complications in some patients, but knows that your patient has an allergy to this new medication so it warns you and provides a list of alternatives.

While this system is still in the process of going live, I am very hopeful it helps the healthcare system. I don't believe it will fix the system however I do believe medication errors, outside of emergency situations such as cardiac arrest, will be reduced.

Add in a strong AI and a large majority of actual diagnosis, rather than suggested diagnosis, may be accurately determined.

The summary is misleading a best (2)

DarthBobo (152187) | about a year and a half ago | (#42890385)

Probably because its a summary of a press release, rather than the actual paper. This was a computer simulation exercise - a model. No patients were actually treated. There was no prescribing. There were no superior outcomes. Its all hypothetical.

Could an AI outperform an MD? Sure, could happen and probably will eventually. But this model doesn't show that. It just shows that its easier to model health care in silicon than the real world. Remember we can cure cancer in mice - models aren't the same thing as reality.

Fire the doctors and the lawyers (0)

Anonymous Coward | about a year and a half ago | (#42890397)

Some may still have jobs if they can hang on to customers who want real in person or over the phone service.

i'm a physician (0)

Anonymous Coward | about a year and a half ago | (#42890425)

I regret going to medical school

Won't happen until insurance companies require it. (1)

Anonymous Coward | about a year and a half ago | (#42890589)

As is often the case with new medical tools designed to avoid common fatal mistakes.

breaking news (0)

Anonymous Coward | about a year and a half ago | (#42890823)

It has been reported that some scientists were found dead after self administering a dangerous drug based on some computer algorithm. Could it be that these are same scientists?

Good! (1)

Anonymous Coward | about a year and a half ago | (#42890957)

Most doctors are pretty bad. In fact, most that do not perform surgery are no more than technicians who have a lot of student loan debt.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>